使用C#.NET从HTML页面中抓取Javascript

时间:2013-05-24 21:17:28

标签: c# c#-4.0 html-agility-pack

我有网站,我需要使用C#HTML Agility Pack废弃。 在源代码中,我需要URL的数组,这是一个Javascript数组。请告诉我如何在Python中获取此数组 从HTML到Javascript的调用是这样的:

<li class="accordion"><a class="xbrlviewer" onClick="javascript:highlight(this);" href="javascript:loadReport(1);">CONSOLIDATED BALANCE SHEETS</a></li>

<script type="text/javascript" language="javascript">
var reports = new Array(61);
    reports[0] = "/Archives/edgar/data/320193/000119312512444068/R1.htm";
    reports[1] = "/Archives/edgar/data/320193/000119312512444068/R2.htm";
    reports[2] = "/Archives/edgar/data/320193/000119312512444068/R3.htm";
    reports[3] = "/Archives/edgar/data/320193/000119312512444068/R4.htm";
    reports[4] = "/Archives/edgar/data/320193/000119312512444068/R5.htm";
    reports[5] = "/Archives/edgar/data/320193/000119312512444068/R6.htm";
    reports[6] = "/Archives/edgar/data/320193/000119312512444068/R7.htm";
    reports[7] = "/Archives/edgar/data/320193/000119312512444068/R8.htm";
    reports[8] = "/Archives/edgar/data/320193/000119312512444068/R9.htm";
    reports[9] = "/Archives/edgar/data/320193/000119312512444068/R10.htm";
    reports[10] = "/Archives/edgar/data/320193/000119312512444068/R11.htm";
    reports[11] = "/Archives/edgar/data/320193/000119312512444068/R12.htm";
    reports[12] = "/Archives/edgar/data/320193/000119312512444068/R13.htm";
    reports[13] = "/Archives/edgar/data/320193/000119312512444068/R14.htm";
    reports[14] = "/Archives/edgar/data/320193/000119312512444068/R15.htm";
    reports[15] = "/Archives/edgar/data/320193/000119312512444068/R16.htm";
    reports[16] = "/Archives/edgar/data/320193/000119312512444068/R17.htm";
    reports[17] = "/Archives/edgar/data/320193/000119312512444068/R18.htm";
    reports[18] = "/Archives/edgar/data/320193/000119312512444068/R19.htm";
    reports[19] = "/Archives/edgar/data/320193/000119312512444068/R20.htm";
    reports[20] = "/Archives/edgar/data/320193/000119312512444068/R21.htm";
    reports[21] = "/Archives/edgar/data/320193/000119312512444068/R22.htm";
    reports[22] = "/Archives/edgar/data/320193/000119312512444068/R23.htm";
    reports[23] = "/Archives/edgar/data/320193/000119312512444068/R24.htm";
    reports[24] = "/Archives/edgar/data/320193/000119312512444068/R25.htm";
    reports[25] = "/Archives/edgar/data/320193/000119312512444068/R26.htm";
    reports[26] = "/Archives/edgar/data/320193/000119312512444068/R27.htm";
    reports[27] = "/Archives/edgar/data/320193/000119312512444068/R28.htm";
    reports[28] = "/Archives/edgar/data/320193/000119312512444068/R29.htm";
    reports[29] = "/Archives/edgar/data/320193/000119312512444068/R30.htm";
    reports[30] = "/Archives/edgar/data/320193/000119312512444068/R31.htm";
    reports[31] = "/Archives/edgar/data/320193/000119312512444068/R32.htm";
    reports[32] = "/Archives/edgar/data/320193/000119312512444068/R33.htm";
    reports[33] = "/Archives/edgar/data/320193/000119312512444068/R34.htm";
    reports[34] = "/Archives/edgar/data/320193/000119312512444068/R35.htm";
    reports[35] = "/Archives/edgar/data/320193/000119312512444068/R36.htm";
    reports[36] = "/Archives/edgar/data/320193/000119312512444068/R37.htm";
    reports[37] = "/Archives/edgar/data/320193/000119312512444068/R38.htm";
    reports[38] = "/Archives/edgar/data/320193/000119312512444068/R39.htm";
    reports[39] = "/Archives/edgar/data/320193/000119312512444068/R40.htm";
    reports[40] = "/Archives/edgar/data/320193/000119312512444068/R41.htm";
    reports[41] = "/Archives/edgar/data/320193/000119312512444068/R42.htm";
    reports[42] = "/Archives/edgar/data/320193/000119312512444068/R43.htm";
    reports[43] = "/Archives/edgar/data/320193/000119312512444068/R44.htm";
    reports[44] = "/Archives/edgar/data/320193/000119312512444068/R45.htm";
    reports[45] = "/Archives/edgar/data/320193/000119312512444068/R46.htm";
    reports[46] = "/Archives/edgar/data/320193/000119312512444068/R47.htm";
    reports[47] = "/Archives/edgar/data/320193/000119312512444068/R48.htm";
    reports[48] = "/Archives/edgar/data/320193/000119312512444068/R49.htm";
    reports[49] = "/Archives/edgar/data/320193/000119312512444068/R50.htm";
    reports[50] = "/Archives/edgar/data/320193/000119312512444068/R51.htm";
    reports[51] = "/Archives/edgar/data/320193/000119312512444068/R52.htm";
    reports[52] = "/Archives/edgar/data/320193/000119312512444068/R53.htm";
    reports[53] = "/Archives/edgar/data/320193/000119312512444068/R54.htm";
    reports[54] = "/Archives/edgar/data/320193/000119312512444068/R55.htm";
    reports[55] = "/Archives/edgar/data/320193/000119312512444068/R56.htm";
    reports[56] = "/Archives/edgar/data/320193/000119312512444068/R57.htm";
    reports[57] = "/Archives/edgar/data/320193/000119312512444068/R58.htm";
    reports[58] = "/Archives/edgar/data/320193/000119312512444068/R59.htm";
    reports[59] = "/Archives/edgar/data/320193/000119312512444068/R60.htm";
    reports[60] = 'all';

0 个答案:

没有答案